[](https://discord.gg/qUtxnK2NMf)
# Aurora
[](https://discord.gg/agora-999382051935506503) [](https://www.youtube.com/@kyegomez3242) [](https://www.linkedin.com/in/kye-g-38759a207/) [](https://x.com/kyegomezb)
Community and Open Source Implementation of the paper: "Aurora: A Foundation Model of the Atmosphere" in PyTorch: [Paper link](https://arxiv.org/abs/2405.13063)
## Install
```bash
pip3 install aurora-torch
```
## Example
```python
import torch
from aurora_torch.main import SwinTransformerUNet3D
from loguru import logger
# Test with random input tensor of shape (B, D, H, W, C)
B, D, H, W, C = 2, 16, 64, 64, 32
model = SwinTransformerUNet3D(input_dim=C, output_dim=C)
input_tensor = torch.rand(B, D, H, W, C)
# Forward pass through the model
output = model(input_tensor)
logger.info(f"Output shape: {output.shape}")
```
# License
MIT
# Bibtex
```bibtex
@misc{bodnar2024aurora,
title={Aurora: A Foundation Model of the Atmosphere},
author={Cristian Bodnar and Wessel P. Bruinsma and Ana Lucic and Megan Stanley and Johannes Brandstetter and Patrick Garvan and Maik Riechert and Jonathan Weyn and Haiyu Dong and Anna Vaughan and Jayesh K. Gupta and Kit Tambiratnam and Alex Archibald and Elizabeth Heider and Max Welling and Richard E. Turner and Paris Perdikaris},
year={2024},
eprint={2405.13063},
archivePrefix={arXiv},
primaryClass={physics.ao-ph}
}
```
# References
- [Blog Release: Introducing Aurora: The first large-scale foundation model of the atmosphere](https://www.microsoft.com/en-us/research/blog/introducing-aurora-the-first-large-scale-foundation-model-of-the-atmosphere/)
- [Paper Link](https://arxiv.org/abs/2405.13063)
<!-- - [Microsoft Twitter Thread]() -->
Raw data
{
"_id": null,
"home_page": "https://github.com/kyegomez/Aurora",
"name": "aurora-torch",
"maintainer": null,
"docs_url": null,
"requires_python": "<4.0,>=3.10",
"maintainer_email": null,
"keywords": "artificial intelligence, deep learning, optimizers, Prompt Engineering",
"author": "Kye Gomez",
"author_email": "kye@apac.ai",
"download_url": "https://files.pythonhosted.org/packages/c7/ba/109a17c847013033739c7a10b4a5e1b7e09d2ffb1ae479c6166eeaf06868/aurora_torch-0.0.9.tar.gz",
"platform": null,
"description": "[](https://discord.gg/qUtxnK2NMf)\n\n# Aurora\n[](https://discord.gg/agora-999382051935506503) [](https://www.youtube.com/@kyegomez3242) [](https://www.linkedin.com/in/kye-g-38759a207/) [](https://x.com/kyegomezb)\n\n\n\n\nCommunity and Open Source Implementation of the paper: \"Aurora: A Foundation Model of the Atmosphere\" in PyTorch: [Paper link](https://arxiv.org/abs/2405.13063)\n\n\n## Install\n```bash\npip3 install aurora-torch\n```\n\n\n## Example\n```python\nimport torch\nfrom aurora_torch.main import SwinTransformerUNet3D\nfrom loguru import logger\n\n# Test with random input tensor of shape (B, D, H, W, C)\nB, D, H, W, C = 2, 16, 64, 64, 32\nmodel = SwinTransformerUNet3D(input_dim=C, output_dim=C)\ninput_tensor = torch.rand(B, D, H, W, C)\n\n# Forward pass through the model\noutput = model(input_tensor)\nlogger.info(f\"Output shape: {output.shape}\")\n\n```\n\n\n# License\nMIT\n\n\n# Bibtex\n```bibtex\n@misc{bodnar2024aurora,\n title={Aurora: A Foundation Model of the Atmosphere}, \n author={Cristian Bodnar and Wessel P. Bruinsma and Ana Lucic and Megan Stanley and Johannes Brandstetter and Patrick Garvan and Maik Riechert and Jonathan Weyn and Haiyu Dong and Anna Vaughan and Jayesh K. Gupta and Kit Tambiratnam and Alex Archibald and Elizabeth Heider and Max Welling and Richard E. Turner and Paris Perdikaris},\n year={2024},\n eprint={2405.13063},\n archivePrefix={arXiv},\n primaryClass={physics.ao-ph}\n}\n```\n\n# References\n\n- [Blog Release: Introducing Aurora: The first large-scale foundation model of the atmosphere](https://www.microsoft.com/en-us/research/blog/introducing-aurora-the-first-large-scale-foundation-model-of-the-atmosphere/)\n\n- [Paper Link](https://arxiv.org/abs/2405.13063)\n\n<!-- - [Microsoft Twitter Thread]() -->",
"bugtrack_url": null,
"license": "MIT",
"summary": "Weather Swarm - Pytorch",
"version": "0.0.9",
"project_urls": {
"Documentation": "https://github.com/kyegomez/Aurora",
"Homepage": "https://github.com/kyegomez/Aurora",
"Repository": "https://github.com/kyegomez/Aurora"
},
"split_keywords": [
"artificial intelligence",
" deep learning",
" optimizers",
" prompt engineering"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "a7f517f5139fde08df3eb9edf53c250811d635082af7661ddb12abee20abbd5e",
"md5": "e405ae63f83d2021bd9911d84ea560c5",
"sha256": "868ee299337992912db5bee2da910eee356800795f79a703818a2c23bd72cfa7"
},
"downloads": -1,
"filename": "aurora_torch-0.0.9-py3-none-any.whl",
"has_sig": false,
"md5_digest": "e405ae63f83d2021bd9911d84ea560c5",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": "<4.0,>=3.10",
"size": 5016,
"upload_time": "2024-09-09T18:24:59",
"upload_time_iso_8601": "2024-09-09T18:24:59.332007Z",
"url": "https://files.pythonhosted.org/packages/a7/f5/17f5139fde08df3eb9edf53c250811d635082af7661ddb12abee20abbd5e/aurora_torch-0.0.9-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "c7ba109a17c847013033739c7a10b4a5e1b7e09d2ffb1ae479c6166eeaf06868",
"md5": "cf74adff2485b2bb901684642ba307f8",
"sha256": "f8e91787ee7b09eee7f69bf1b66ba8b09f045db79411a4b149aea63a95ced8c5"
},
"downloads": -1,
"filename": "aurora_torch-0.0.9.tar.gz",
"has_sig": false,
"md5_digest": "cf74adff2485b2bb901684642ba307f8",
"packagetype": "sdist",
"python_version": "source",
"requires_python": "<4.0,>=3.10",
"size": 4677,
"upload_time": "2024-09-09T18:25:00",
"upload_time_iso_8601": "2024-09-09T18:25:00.770853Z",
"url": "https://files.pythonhosted.org/packages/c7/ba/109a17c847013033739c7a10b4a5e1b7e09d2ffb1ae479c6166eeaf06868/aurora_torch-0.0.9.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-09-09 18:25:00",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "kyegomez",
"github_project": "Aurora",
"travis_ci": false,
"coveralls": false,
"github_actions": true,
"requirements": [],
"lcname": "aurora-torch"
}
JSON
